Hardware · Apple Silicon

What AI models can the Apple M2 (16 GB) run?

Unified memory: 16.0 GB
Usable for models: 10.7 GB
Memory bandwidth: 100 GB/s
FP16 compute: 3.6 TFLOPS
Released: 2022

macOS lets the GPU use roughly two-thirds to three-quarters of unified memory by default, so we plan around that figure rather than the full 16.0 GB.

Specifications

Maker	Apple Silicon
Type	Apple silicon (system on a chip)
Chip	Apple M2
Unified memory	16.0 GB
Usable for AI models	10.7 GB
Memory bandwidth	100 GB/s
FP16 compute	3.6 TFLOPS
Interface	UNIFIED
Released	2022

4 products with the Apple M2 (16 GB)

MacBook Air (M2, 2022)Apple · Laptop · 8, 16 or 24 GB · from $1,199Maker’s page (opens in a new tab)
MacBook Air (15-inch, M2, 2023)Apple · Laptop · 8, 16 or 24 GB · from $1,299Maker’s page (opens in a new tab)
MacBook Pro (13-inch, M2, 2022)Apple · Laptop · 8, 16 or 24 GB · from $1,299Maker’s page (opens in a new tab)
Mac mini (2023) (M2 or M2 Pro)Apple · Mini PC · 8, 16, 24 or 32 GB · from $599Maker’s page (opens in a new tab)

Best LLMs for the Apple M2 (16 GB)

Grade · points	Model	Quant	Memory	Speed	Fit
81 ptsGreat (A) · 81 of 100 points: Model quality 36.2/45, Memory fit 24.0/25, Speed 6.4/15, Memory use 15.0/15	Gemma 4 12BGoogle	`Q5_K_M`	10.6 GB	7.3 tok/s	Tight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 15.0/15	Ornith 1.5 9BDeepReinforce	`Q4_K_M`	7.6 GB	11.0 tok/s	Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 15.0/15	Qwen3.5 9BAlibaba	`Q4_K_M`	7.6 GB	11.0 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 7.8/15, Memory use 15.0/15	Ornith 1.0 9BDeepReinforce	`Q4_K_M`	7.6 GB	11.0 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 15.0/15	TMax 9BAi2	`Q4_K_M`	7.2 GB	11.8 tok/s	Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15	Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	`Q4_K_M`	6.5 GB	40.7 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15	UI-Mate 9BTencent	`Q4_K_M`	7.5 GB	11.2 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 7.9/15, Memory use 15.0/15	UI-Venus 2 9BAnt Group (inclusionAI)	`Q4_K_M`	7.5 GB	11.2 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 15.0/15	Granite 4.2 8BIBM	`Q4_K_M`	8.2 GB	12.0 tok/s	Runs well
76 ptsGreat (A) · 76 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 13.9/15	Gemma 4 E4BGoogle	`Q4_K_M`	6.5 GB	13.2 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 14.5/15	LFM2.5 8B-A1BLiquid AI	`Q4_K_M`	6.7 GB	35.2 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 15.0/15	DeepSeek R1 0528 Qwen3 8BDeepSeek	`Q4_K_M`	7.7 GB	12.9 tok/s	Runs well

Best Image models for the Apple M2 (16 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
83 ptsGreat (A) · 83 of 100 points: Model quality 34.4/45, Memory fit 23.0/25, Speed 11.2/15, Memory use 15.0/15	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	10.2 GB	18 s	Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 35.2/45, Memory fit 23.0/25, Speed 6.1/15, Memory use 15.0/15	Z-Image TurboAlibaba (Tongyi)	`Q4 GGUF`	10.1 GB	60 s	Tight fit
77 ptsGreat (A) · 77 of 100 points: Model quality 35.2/45, Memory fit 20.0/25, Speed 7.1/15, Memory use 15.0/15	FLUX.2 [klein] 9BBlack Forest Labs	`Q4 GGUF`	8.0 GB	45 s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 9.3/15, Memory use 15.0/15	DreamShaper XL v2 TurboLykon	`FP16`	8.9 GB	26 s	Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 34.3/45, Memory fit 23.0/25, Speed 2.4/15, Memory use 15.0/15	Z-ImageAlibaba (Tongyi)	`Q4 GGUF`	10.1 GB	6.8 min	Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 23.8/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 12.0/15	SDXL-Lightning (4-step)ByteDance	`FP8`	5.6 GB	13 s	Runs well

Best Video models for the Apple M2 (16 GB)

Grade · points	Model	Precision	Memory	Time per output	Fit
64 ptsGood (B) · 64 of 100 points: Model quality 22.1/45, Memory fit 20.0/25, Speed 9.3/15, Memory use 13.0/15	LTX-Video 2BLightricks	`FP8`	6.1 GB	7.8 min	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 24.8/45, Memory fit 20.0/25, Speed 2.8/15, Memory use 15.0/15	Wan 2.1 T2V 1.3BAlibaba	`FP16`	8.4 GB	83.7 min	Runs well
62 ptsGood (B) · 62 of 100 points: Model quality 24.3/45, Memory fit 20.0/25, Speed 2.9/15, Memory use 15.0/15	Wan 2.1 VACE 1.3BAlibaba	`FP8`	8.0 GB	81.6 min	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 10.1/15, Memory use 10.1/15	AnimateDiff v3 (SD 1.5)Shanghai AI Lab	`FP16`	4.7 GB	6.6 min	Runs well
60 ptsGood (B) · 60 of 100 points: Model quality 20.3/45, Memory fit 20.0/25, Speed 5.7/15, Memory use 15.0/15	CogVideoX 2BZhipu AI	`FP16`	7.9 GB	20.9 min	Runs well

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.